Mitarbeiter

Deutsches Zentrum für Luft- und Raumfahrt (DLR)
Institut für Robotik und Mechatronik
Perzeption und Kognition
Oberpfaffenhofen
Münchener Str. 20
82234 Weßling

Telefon:	+49 8153 28-1097
E-Mail:	Jianxiang Feng

I am a research staff at the Institute of Robotics and Mechatronics (RM), the German Aerospace Center (DLR). I was born in Guangzhou, China and did my Bachelor in Beijing and Master in Munich, Germany. Please feel free to visit my Google Scholar, and follow me on Linkedin. My research aims to facilitate cognitive behaviors on robots including trustworthy scene understanding and efficient learning capability with probabilistic machine learning methods.

Short CV

Jianxiang Feng received his bachelor degree in electronic engineering from Beijing University of Posts and Telecommunication (BUPT), China (2011-2015) and his master degree in electronic and information technology from Technical University of Munich (TUM), Germany (2016-2019). Since August 2019, he is a research scientist at the Institute of Robotics and Mechatronics (RM), the German Aerospace Center (DLR), Germany. His research interests reside in the intersection of robotics and machine learning. At DLR, he is one of the developers of the DLR assistive robot, EDAN - a robotic platform to assist humans with motor impairments.

 

Research Keywords

• Introspective methods for robot perception.
• Bayesian machine learning.
• Assistive robotics incl. perception and planning.

 

Projects

• SMiLE2gether

 

Supervision

• [MT2] Master Thesis: "Graph Neural Networks for Knowledge Transfer in Robotic Assembly Sequence Planning" by Matan Atad, co-supervision with Maximilian Durner, Ismael Rodriguezbrena, finished.
• [MT1] Master Thesis: "Scene Graph Generation from Visual perception for Task and Motion Planning" by Mohit Kumar, co-supervision with Samuel Bustamante, finished.

 

Publications

 

• [5] Jianxiang Feng, Jongseok Lee, Maximilian Durner, Rudolph Triebel: Bayesian Active Learning for Sim-to-Real Robotic Perception, In the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
• [4] Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, Jongseok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, Muhammad Shahzad, Wen Yang, Richard Bamler and Xiao Xiang Zhu: A Survey of Uncertainty in Deep Neural Networks (preprint).
• [3] Jongseok Lee, Jianxiang Feng, Matthias Humt, Marcus G. Müller and Rudolph Triebel: Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes, in 5th Conference on Robot Learning (CoRL), London, United Kingdom, 2021. ISSN 2640-3498
• [2] Jongseok Lee, Matthias Humt, Jianxiang Feng, Rudolph Triebel: Estimating Model Uncertainty of Neural Networks in Sparse Information Form, in the Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119:5702-5713, 2020.
• [1] Jianxiang Feng ^*, Maximilian Durner^*, Zoltán-Csaba Márton, Bálint-Benczédi Ferenc, Rudolph Triebel. (2022): Introspective Robot Perception Using Smoothed Predictions from Bayesian Neural Networks. In Robotics Research. ISRR 2019. Springer Proceedings in Advanced Robotics, vol 20. Springer, Cham.

 

Academic Service

Lists of venues that I served as a reviewer:

• IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• IEEE International Conference on Robotics and Automation (ICRA)
• Conference on Robot Learning (CoRL)

Co-organized Workshops:

• Probabilistic Robotics In the age of Deep Learning [IROS2022]